Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3311 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.8256. Min Act: -0.0000

Data Index: 155785 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.3922. Min Act: -0.0000

Data Index: 330015 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.3568. Min Act: -0.0000

Data Index: 507668 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.3477. Min Act: -0.0000

Data Index: 849136 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.2135. Min Act: -0.0000

Data Index: 541998 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 2.8256. Min Range: -2.8256

Max Act: 2.1181. Min Act: -0.0000

Data Index: 371039 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.9848. Min Act: -0.0000

Data Index: 613762 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.9772. Min Act: -0.0000

Data Index: 262608 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.8806. Min Act: -0.0000

Data Index: 1193462 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.8695. Min Act: -0.0000

Data Index: 967806 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.7526. Min Act: -0.0000

Data Index: 1195827 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.8628. Min Act: -0.0000

Data Index: 662715 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.8368. Min Act: -0.0000

Data Index: 2018 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.9092. Min Act: -0.0000

Data Index: 19663 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.8014. Min Act: -0.0000

Data Index: 1300236 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.7835. Min Act: -0.0000

Data Index: 1173840 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.7781. Min Act: -0.0000

Data Index: 1007376 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.7678. Min Act: -0.0000

Data Index: 238544 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.6727. Min Act: -0.0000

Data Index: 450752 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 2.8256. Min Range: -2.8256

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1259198 (C4 (Web Text))

Max Activating Token Index: 536